Experimental study of stability prediction for high-speed robotic milling of aluminum

It has been fully demonstrated that the regenerative chatter theory is applicable for predicting chatter-free milling parameters for computer numerical control machine tools, but researchers are still arguing whether it is effective for robotic milling processes. The main reason is that the robot's modes greatly shift, depending on its varying dynamic parameters and joint configurations. More experimental investigations are required to study and better understand the mechanism of vibration in robotic machining. The present paper is focusing on finding experimental support for chatter-free prediction in robot high-speed milling by the regenerative chatter theory. Modal tests are first conducted on a milling robot and used to predict stability lobes by zeroth order approximation. A number of high-speed slotting tests are then carried out to verify the prediction results. Thus, the regenerative chatter theory is proved to be also applicable to robotic high-speed milling. Furthermore, low-frequency modes of the robot structure are investigated by more modal experiments involving a laser tracker and a displacement sensor. The low-frequency modes are identified as the main part of the prediction error of the zeroth order approximation method, which could also be dominant in low-speed robotic milling processes. In addition, robots are different from computer numerical control machines in terms of stiffness, trajectory following error, forced vibration, and motion coupling. These long-period trend terms have to be carefully taken into account in the regenerative chatter theory for robotic high-speed milling.